This instance will be upgraded to Heptapod 0.21.0rc2 on 2021-04-16 at 14:00 UTC+2 (a few minutes of down time)

absorb.py 40.8 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
# absorb.py
#
# Copyright 2016 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

"""apply working directory changes to changesets (EXPERIMENTAL)

The absorb extension provides a command to use annotate information to
amend modified chunks into the corresponding non-public changesets.

::

    [absorb]
    # only check 50 recent non-public changesets at most
17
    max-stack-size = 50
18
    # whether to add noise to new commits to avoid obsolescence cycle
19
    add-noise = 1
20
    # make `amend --correlated` a shortcut to the main command
21
    amend-flag = correlated
22 23

    [color]
24
    absorb.description = yellow
25 26 27 28
    absorb.node = blue bold
    absorb.path = bold
"""

29 30 31 32 33
# TODO:
#  * Rename config items to [commands] namespace
#  * Converge getdraftstack() with other code in core
#  * move many attributes on fixupstate to be private

34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50
from __future__ import absolute_import

import collections

from mercurial.i18n import _
from mercurial import (
    cmdutil,
    commands,
    context,
    crecord,
    error,
    linelog,
    mdiff,
    node,
    obsolete,
    patch,
    phases,
51
    pycompat,
52
    registrar,
53
    rewriteutil,
54 55 56
    scmutil,
    util,
)
57
from mercurial.utils import stringutil
58 59 60 61 62

# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
63
testedwith = b'ships-with-hg-core'
64 65 66 67 68 69 70

cmdtable = {}
command = registrar.command(cmdtable)

configtable = {}
configitem = registrar.configitem(configtable)

71 72 73
configitem(b'absorb', b'add-noise', default=True)
configitem(b'absorb', b'amend-flag', default=None)
configitem(b'absorb', b'max-stack-size', default=50)
74 75

colortable = {
76 77 78
    b'absorb.description': b'yellow',
    b'absorb.node': b'blue bold',
    b'absorb.path': b'bold',
79 80 81 82
}

defaultdict = collections.defaultdict

83

84 85
class nullui(object):
    """blank ui object doing nothing"""
86

87 88 89 90 91 92 93
    debugflag = False
    verbose = False
    quiet = True

    def __getitem__(name):
        def nullfunc(*args, **kwds):
            return
94

95 96
        return nullfunc

97

98 99
class emptyfilecontext(object):
    """minimal filecontext representing an empty file"""
100

101
    def data(self):
102
        return b''
103 104 105 106

    def node(self):
        return node.nullid

107

108 109 110 111 112 113 114 115 116 117
def uniq(lst):
    """list -> list. remove duplicated items without changing the order"""
    seen = set()
    result = []
    for x in lst:
        if x not in seen:
            seen.add(x)
            result.append(x)
    return result

118

119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140
def getdraftstack(headctx, limit=None):
    """(ctx, int?) -> [ctx]. get a linear stack of non-public changesets.

    changesets are sorted in topo order, oldest first.
    return at most limit items, if limit is a positive number.

    merges are considered as non-draft as well. i.e. every commit
    returned has and only has 1 parent.
    """
    ctx = headctx
    result = []
    while ctx.phase() != phases.public:
        if limit and len(result) >= limit:
            break
        parents = ctx.parents()
        if len(parents) != 1:
            break
        result.append(ctx)
        ctx = parents[0]
    result.reverse()
    return result

141

142
def getfilestack(stack, path, seenfctxs=None):
143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178
    """([ctx], str, set) -> [fctx], {ctx: fctx}

    stack is a list of contexts, from old to new. usually they are what
    "getdraftstack" returns.

    follows renames, but not copies.

    seenfctxs is a set of filecontexts that will be considered "immutable".
    they are usually what this function returned in earlier calls, useful
    to avoid issues that a file was "moved" to multiple places and was then
    modified differently, like: "a" was copied to "b", "a" was also copied to
    "c" and then "a" was deleted, then both "b" and "c" were "moved" from "a"
    and we enforce only one of them to be able to affect "a"'s content.

    return an empty list and an empty dict, if the specified path does not
    exist in stack[-1] (the top of the stack).

    otherwise, return a list of de-duplicated filecontexts, and the map to
    convert ctx in the stack to fctx, for possible mutable fctxs. the first item
    of the list would be outside the stack and should be considered immutable.
    the remaining items are within the stack.

    for example, given the following changelog and corresponding filelog
    revisions:

      changelog: 3----4----5----6----7
      filelog:   x    0----1----1----2 (x: no such file yet)

    - if stack = [5, 6, 7], returns ([0, 1, 2], {5: 1, 6: 1, 7: 2})
    - if stack = [3, 4, 5], returns ([e, 0, 1], {4: 0, 5: 1}), where "e" is a
      dummy empty filecontext.
    - if stack = [2], returns ([], {})
    - if stack = [7], returns ([1, 2], {7: 2})
    - if stack = [6, 7], returns ([1, 2], {6: 1, 7: 2}), although {6: 1} can be
      removed, since 1 is immutable.
    """
179 180
    if seenfctxs is None:
        seenfctxs = set()
181 182 183 184 185 186 187 188
    assert stack

    if path not in stack[-1]:
        return [], {}

    fctxs = []
    fctxmap = {}

189
    pctx = stack[0].p1()  # the public (immutable) ctx we stop at
190
    for ctx in reversed(stack):
191
        if path not in ctx:  # the file is added in the next commit
192 193 194 195
            pctx = ctx
            break
        fctx = ctx[path]
        fctxs.append(fctx)
196 197
        if fctx in seenfctxs:  # treat fctx as the immutable one
            pctx = None  # do not add another immutable fctx
198
            break
199
        fctxmap[ctx] = fctx  # only for mutable fctxs
200 201
        copy = fctx.copysource()
        if copy:
202 203
            path = copy  # follow rename
            if path in ctx:  # but do not follow copy
204 205 206
                pctx = ctx.p1()
                break

207
    if pctx is not None:  # need an extra immutable fctx
208 209 210 211 212 213 214 215 216 217 218 219 220 221 222
        if path in pctx:
            fctxs.append(pctx[path])
        else:
            fctxs.append(emptyfilecontext())

    fctxs.reverse()
    # note: we rely on a property of hg: filerev is not reused for linear
    # history. i.e. it's impossible to have:
    #   changelog:  4----5----6 (linear, no merges)
    #   filelog:    1----2----1
    #                         ^ reuse filerev (impossible)
    # because parents are part of the hash. if that's not true, we need to
    # remove uniq and find a different way to identify fctxs.
    return uniq(fctxs), fctxmap

223

224 225 226 227
class overlaystore(patch.filestore):
    """read-only, hybrid store based on a dict and ctx.
    memworkingcopy: {path: content}, overrides file contents.
    """
228

229 230 231 232 233 234 235 236 237 238 239 240 241 242
    def __init__(self, basectx, memworkingcopy):
        self.basectx = basectx
        self.memworkingcopy = memworkingcopy

    def getfile(self, path):
        """comply with mercurial.patch.filestore.getfile"""
        if path not in self.basectx:
            return None, None, None
        fctx = self.basectx[path]
        if path in self.memworkingcopy:
            content = self.memworkingcopy[path]
        else:
            content = fctx.data()
        mode = (fctx.islink(), fctx.isexec())
243 244
        copy = fctx.copysource()
        return content, mode, copy
245

246

247
def overlaycontext(memworkingcopy, ctx, parents=None, extra=None, desc=None):
248 249 250 251 252 253 254 255
    """({path: content}, ctx, (p1node, p2node)?, {}?) -> memctx
    memworkingcopy overrides file contents.
    """
    # parents must contain 2 items: (node1, node2)
    if parents is None:
        parents = ctx.repo().changelog.parents(ctx.node())
    if extra is None:
        extra = ctx.extra()
256 257
    if desc is None:
        desc = ctx.description()
258 259
    date = ctx.date()
    user = ctx.user()
260
    files = set(ctx.files()).union(memworkingcopy)
261 262
    store = overlaystore(ctx, memworkingcopy)
    return context.memctx(
263 264 265 266 267 268 269 270 271 272 273
        repo=ctx.repo(),
        parents=parents,
        text=desc,
        files=files,
        filectxfn=store,
        user=user,
        date=date,
        branch=None,
        extra=extra,
    )

274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296

class filefixupstate(object):
    """state needed to apply fixups to a single file

    internally, it keeps file contents of several revisions and a linelog.

    the linelog uses odd revision numbers for original contents (fctxs passed
    to __init__), and even revision numbers for fixups, like:

        linelog rev 1: self.fctxs[0] (from an immutable "public" changeset)
        linelog rev 2: fixups made to self.fctxs[0]
        linelog rev 3: self.fctxs[1] (a child of fctxs[0])
        linelog rev 4: fixups made to self.fctxs[1]
        ...

    a typical use is like:

        1. call diffwith, to calculate self.fixups
        2. (optionally), present self.fixups to the user, or change it
        3. call apply, to apply changes
        4. read results from "finalcontents", or call getfinalcontent
    """

297
    def __init__(self, fctxs, path, ui=None, opts=None):
298 299 300 301 302 303
        """([fctx], ui or None) -> None

        fctxs should be linear, and sorted by topo order - oldest first.
        fctxs[0] will be considered as "immutable" and will not be changed.
        """
        self.fctxs = fctxs
304
        self.path = path
305 306 307 308 309
        self.ui = ui or nullui()
        self.opts = opts or {}

        # following fields are built from fctxs. they exist for perf reason
        self.contents = [f.data() for f in fctxs]
310
        self.contentlines = pycompat.maplist(mdiff.splitnewlines, self.contents)
311 312 313 314 315
        self.linelog = self._buildlinelog()
        if self.ui.debugflag:
            assert self._checkoutlinelog() == self.contents

        # following fields will be filled later
316 317 318 319
        self.chunkstats = [0, 0]  # [adopted, total : int]
        self.targetlines = []  # [str]
        self.fixups = []  # [(linelog rev, a1, a2, b1, b2)]
        self.finalcontents = []  # [str]
320
        self.ctxaffected = set()
321

322
    def diffwith(self, targetfctx, fm=None):
323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340
        """calculate fixups needed by examining the differences between
        self.fctxs[-1] and targetfctx, chunk by chunk.

        targetfctx is the target state we move towards. we may or may not be
        able to get there because not all modified chunks can be amended into
        a non-public fctx unambiguously.

        call this only once, before apply().

        update self.fixups, self.chunkstats, and self.targetlines.
        """
        a = self.contents[-1]
        alines = self.contentlines[-1]
        b = targetfctx.data()
        blines = mdiff.splitnewlines(b)
        self.targetlines = blines

        self.linelog.annotate(self.linelog.maxrev)
341
        annotated = self.linelog.annotateresult  # [(linelog rev, linenum)]
342 343 344 345 346 347 348 349 350
        assert len(annotated) == len(alines)
        # add a dummy end line to make insertion at the end easier
        if annotated:
            dummyendline = (annotated[-1][0], annotated[-1][1] + 1)
            annotated.append(dummyendline)

        # analyse diff blocks
        for chunk in self._alldiffchunks(a, b, alines, blines):
            newfixups = self._analysediffchunk(chunk, annotated)
351
            self.chunkstats[0] += bool(newfixups)  # 1 or 0
352 353
            self.chunkstats[1] += 1
            self.fixups += newfixups
354 355
            if fm is not None:
                self._showchanges(fm, alines, blines, chunk, newfixups)
356 357 358 359 360 361 362 363 364 365 366 367

    def apply(self):
        """apply self.fixups. update self.linelog, self.finalcontents.

        call this only once, before getfinalcontent(), after diffwith().
        """
        # the following is unnecessary, as it's done by "diffwith":
        #   self.linelog.annotate(self.linelog.maxrev)
        for rev, a1, a2, b1, b2 in reversed(self.fixups):
            blines = self.targetlines[b1:b2]
            if self.ui.debugflag:
                idx = (max(rev - 1, 0)) // 2
368
                self.ui.write(
369
                    _(b'%s: chunk %d:%d -> %d lines\n')
370 371
                    % (node.short(self.fctxs[idx].node()), a1, a2, len(blines))
                )
372
            self.linelog.replacelines(rev, a1, a2, b1, b2)
373
        if self.opts.get(b'edit_lines', False):
374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404
            self.finalcontents = self._checkoutlinelogwithedits()
        else:
            self.finalcontents = self._checkoutlinelog()

    def getfinalcontent(self, fctx):
        """(fctx) -> str. get modified file content for a given filecontext"""
        idx = self.fctxs.index(fctx)
        return self.finalcontents[idx]

    def _analysediffchunk(self, chunk, annotated):
        """analyse a different chunk and return new fixups found

        return [] if no lines from the chunk can be safely applied.

        the chunk (or lines) cannot be safely applied, if, for example:
          - the modified (deleted) lines belong to a public changeset
            (self.fctxs[0])
          - the chunk is a pure insertion and the adjacent lines (at most 2
            lines) belong to different non-public changesets, or do not belong
            to any non-public changesets.
          - the chunk is modifying lines from different changesets.
            in this case, if the number of lines deleted equals to the number
            of lines added, assume it's a simple 1:1 map (could be wrong).
            otherwise, give up.
          - the chunk is modifying lines from a single non-public changeset,
            but other revisions touch the area as well. i.e. the lines are
            not continuous as seen from the linelog.
        """
        a1, a2, b1, b2 = chunk
        # find involved indexes from annotate result
        involved = annotated[a1:a2]
405
        if not involved and annotated:  # a1 == a2 and a is not empty
406 407
            # pure insertion, check nearby lines. ignore lines belong
            # to the public (first) changeset (i.e. annotated[i][0] == 1)
408
            nearbylinenums = {a2, max(0, a1 - 1)}
409 410 411
            involved = [
                annotated[i] for i in nearbylinenums if annotated[i][0] != 1
            ]
412
        involvedrevs = list({r for r, l in involved})
413 414 415 416 417 418 419 420 421
        newfixups = []
        if len(involvedrevs) == 1 and self._iscontinuous(a1, a2 - 1, True):
            # chunk belongs to a single revision
            rev = involvedrevs[0]
            if rev > 1:
                fixuprev = rev + 1
                newfixups.append((fixuprev, a1, a2, b1, b2))
        elif a2 - a1 == b2 - b1 or b1 == b2:
            # 1:1 line mapping, or chunk was deleted
422
            for i in pycompat.xrange(a1, a2):
423 424
                rev, linenum = annotated[i]
                if rev > 1:
425
                    if b1 == b2:  # deletion, simply remove that single line
426
                        nb1 = nb2 = 0
427
                    else:  # 1:1 line mapping, change the corresponding rev
428 429 430 431 432 433 434 435 436 437 438
                        nb1 = b1 + i - a1
                        nb2 = nb1 + 1
                    fixuprev = rev + 1
                    newfixups.append((fixuprev, i, i + 1, nb1, nb2))
        return self._optimizefixups(newfixups)

    @staticmethod
    def _alldiffchunks(a, b, alines, blines):
        """like mdiff.allblocks, but only care about differences"""
        blocks = mdiff.allblocks(a, b, lines1=alines, lines2=blines)
        for chunk, btype in blocks:
439
            if btype != b'!':
440 441 442 443 444 445 446 447
                continue
            yield chunk

    def _buildlinelog(self):
        """calculate the initial linelog based on self.content{,line}s.
        this is similar to running a partial "annotate".
        """
        llog = linelog.linelog()
448
        a, alines = b'', []
449
        for i in pycompat.xrange(len(self.contents)):
450 451 452 453 454 455 456 457 458 459 460
            b, blines = self.contents[i], self.contentlines[i]
            llrev = i * 2 + 1
            chunks = self._alldiffchunks(a, b, alines, blines)
            for a1, a2, b1, b2 in reversed(list(chunks)):
                llog.replacelines(llrev, a1, a2, b1, b2)
            a, alines = b, blines
        return llog

    def _checkoutlinelog(self):
        """() -> [str]. check out file contents from linelog"""
        contents = []
461
        for i in pycompat.xrange(len(self.contents)):
462 463
            rev = (i + 1) * 2
            self.linelog.annotate(rev)
464
            content = b''.join(map(self._getline, self.linelog.annotateresult))
465 466 467 468 469 470 471
            contents.append(content)
        return contents

    def _checkoutlinelogwithedits(self):
        """() -> [str]. prompt all lines for edit"""
        alllines = self.linelog.getalllines()
        # header
472 473
        editortext = (
            _(
474 475
                b'HG: editing %s\nHG: "y" means the line to the right '
                b'exists in the changeset to the top\nHG:\n'
476 477 478
            )
            % self.fctxs[-1].path()
        )
479
        # [(idx, fctx)]. hide the dummy emptyfilecontext
480 481 482 483 484
        visiblefctxs = [
            (i, f)
            for i, f in enumerate(self.fctxs)
            if not isinstance(f, emptyfilecontext)
        ]
485
        for i, (j, f) in enumerate(visiblefctxs):
486 487 488
            editortext += _(b'HG: %s/%s %s %s\n') % (
                b'|' * i,
                b'-' * (len(visiblefctxs) - i + 1),
489
                node.short(f.node()),
490
                f.description().split(b'\n', 1)[0],
491
            )
492
        editortext += _(b'HG: %s\n') % (b'|' * len(visiblefctxs))
493 494
        # figure out the lifetime of a line, this is relatively inefficient,
        # but probably fine
495
        lineset = defaultdict(lambda: set())  # {(llrev, linenum): {llrev}}
496 497 498 499 500 501
        for i, f in visiblefctxs:
            self.linelog.annotate((i + 1) * 2)
            for l in self.linelog.annotateresult:
                lineset[l].add(i)
        # append lines
        for l in alllines:
502 503
            editortext += b'    %s : %s' % (
                b''.join(
504
                    [
505
                        (b'y' if i in lineset[l] else b' ')
506 507 508 509 510
                        for i, _f in visiblefctxs
                    ]
                ),
                self._getline(l),
            )
511
        # run editor
512
        editedtext = self.ui.edit(editortext, b'', action=b'absorb')
513
        if not editedtext:
514
            raise error.Abort(_(b'empty editor text'))
515
        # parse edited result
516
        contents = [b''] * len(self.fctxs)
517 518 519
        leftpadpos = 4
        colonpos = leftpadpos + len(visiblefctxs) + 1
        for l in mdiff.splitnewlines(editedtext):
520
            if l.startswith(b'HG:'):
521
                continue
522 523
            if l[colonpos - 1 : colonpos + 2] != b' : ':
                raise error.Abort(_(b'malformed line: %s') % l)
524
            linecontent = l[colonpos + 2 :]
525
            for i, ch in enumerate(
526 527
                pycompat.bytestr(l[leftpadpos : colonpos - 1])
            ):
528
                if ch == b'y':
529 530 531 532 533 534 535 536 537 538
                    contents[visiblefctxs[i][0]] += linecontent
        # chunkstats is hard to calculate if anything changes, therefore
        # set them to just a simple value (1, 1).
        if editedtext != editortext:
            self.chunkstats = [1, 1]
        return contents

    def _getline(self, lineinfo):
        """((rev, linenum)) -> str. convert rev+line number to line content"""
        rev, linenum = lineinfo
539
        if rev & 1:  # odd: original line taken from fctxs
540
            return self.contentlines[rev // 2][linenum]
541
        else:  # even: fixup line from targetfctx
542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576
            return self.targetlines[linenum]

    def _iscontinuous(self, a1, a2, closedinterval=False):
        """(a1, a2 : int) -> bool

        check if these lines are continuous. i.e. no other insertions or
        deletions (from other revisions) among these lines.

        closedinterval decides whether a2 should be included or not. i.e. is
        it [a1, a2), or [a1, a2] ?
        """
        if a1 >= a2:
            return True
        llog = self.linelog
        offset1 = llog.getoffset(a1)
        offset2 = llog.getoffset(a2) + int(closedinterval)
        linesinbetween = llog.getalllines(offset1, offset2)
        return len(linesinbetween) == a2 - a1 + int(closedinterval)

    def _optimizefixups(self, fixups):
        """[(rev, a1, a2, b1, b2)] -> [(rev, a1, a2, b1, b2)].
        merge adjacent fixups to make them less fragmented.
        """
        result = []
        pcurrentchunk = [[-1, -1, -1, -1, -1]]

        def pushchunk():
            if pcurrentchunk[0][0] != -1:
                result.append(tuple(pcurrentchunk[0]))

        for i, chunk in enumerate(fixups):
            rev, a1, a2, b1, b2 = chunk
            lastrev = pcurrentchunk[0][0]
            lasta2 = pcurrentchunk[0][2]
            lastb2 = pcurrentchunk[0][4]
577 578 579 580 581 582
            if (
                a1 == lasta2
                and b1 == lastb2
                and rev == lastrev
                and self._iscontinuous(max(a1 - 1, 0), a1)
            ):
583 584 585 586 587 588 589 590 591
                # merge into currentchunk
                pcurrentchunk[0][2] = a2
                pcurrentchunk[0][4] = b2
            else:
                pushchunk()
                pcurrentchunk[0] = list(chunk)
        pushchunk()
        return result

592 593
    def _showchanges(self, fm, alines, blines, chunk, fixups):
        def trim(line):
594
            if line.endswith(b'\n'):
595
                line = line[:-1]
596
            return line
597 598 599 600 601 602

        # this is not optimized for perf but _showchanges only gets executed
        # with an extra command-line flag.
        a1, a2, b1, b2 = chunk
        aidxs, bidxs = [0] * (a2 - a1), [0] * (b2 - b1)
        for idx, fa1, fa2, fb1, fb2 in fixups:
603
            for i in pycompat.xrange(fa1, fa2):
604
                aidxs[i - a1] = (max(idx, 1) - 1) // 2
605
            for i in pycompat.xrange(fb1, fb2):
606 607
                bidxs[i - b1] = (max(idx, 1) - 1) // 2

608
        fm.startitem()
609
        fm.write(
610 611 612 613
            b'hunk',
            b'        %s\n',
            b'@@ -%d,%d +%d,%d @@' % (a1, a2 - a1, b1, b2 - b1),
            label=b'diff.hunk',
614
        )
615
        fm.data(path=self.path, linetype=b'hunk')
616 617 618

        def writeline(idx, diffchar, line, linetype, linelabel):
            fm.startitem()
619
            node = b''
620 621 622 623
            if idx:
                ctx = self.fctxs[idx]
                fm.context(fctx=ctx)
                node = ctx.hex()
624
                self.ctxaffected.add(ctx.changectx())
625
            fm.write(b'node', b'%-7.7s ', node, label=b'absorb.node')
626
            fm.write(
627 628
                b'diffchar ' + linetype,
                b'%s%s\n',
629 630 631 632
                diffchar,
                line,
                label=linelabel,
            )
633 634 635
            fm.data(path=self.path, linetype=linetype)

        for i in pycompat.xrange(a1, a2):
636
            writeline(
637 638 639 640 641
                aidxs[i - a1],
                b'-',
                trim(alines[i]),
                b'deleted',
                b'diff.deleted',
642
            )
643
        for i in pycompat.xrange(b1, b2):
644
            writeline(
645 646 647 648 649
                bidxs[i - b1],
                b'+',
                trim(blines[i]),
                b'inserted',
                b'diff.inserted',
650 651
            )

652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678

class fixupstate(object):
    """state needed to run absorb

    internally, it keeps paths and filefixupstates.

    a typical use is like filefixupstates:

        1. call diffwith, to calculate fixups
        2. (optionally), present fixups to the user, or edit fixups
        3. call apply, to apply changes to memory
        4. call commit, to commit changes to hg database
    """

    def __init__(self, stack, ui=None, opts=None):
        """([ctx], ui or None) -> None

        stack: should be linear, and sorted by topo order - oldest first.
        all commits in stack are considered mutable.
        """
        assert stack
        self.ui = ui or nullui()
        self.opts = opts or {}
        self.stack = stack
        self.repo = stack[-1].repo().unfiltered()

        # following fields will be filled later
679 680 681 682 683 684 685
        self.paths = []  # [str]
        self.status = None  # ctx.status output
        self.fctxmap = {}  # {path: {ctx: fctx}}
        self.fixupmap = {}  # {path: filefixupstate}
        self.replacemap = {}  # {oldnode: newnode or None}
        self.finalnode = None  # head after all fixups
        self.ctxaffected = set()  # ctx that will be absorbed into
686

687
    def diffwith(self, targetctx, match=None, fm=None):
688 689 690 691 692 693
        """diff and prepare fixups. update self.fixupmap, self.paths"""
        # only care about modified files
        self.status = self.stack[-1].status(targetctx, match)
        self.paths = []
        # but if --edit-lines is used, the user may want to edit files
        # even if they are not modified
694
        editopt = self.opts.get(b'edit_lines')
695 696 697 698 699 700 701 702 703
        if not self.status.modified and editopt and match:
            interestingpaths = match.files()
        else:
            interestingpaths = self.status.modified
        # prepare the filefixupstate
        seenfctxs = set()
        # sorting is necessary to eliminate ambiguity for the "double move"
        # case: "hg cp A B; hg cp A C; hg rm A", then only "B" can affect "A".
        for path in sorted(interestingpaths):
704
            self.ui.debug(b'calculating fixups for %s\n' % path)
705 706 707
            targetfctx = targetctx[path]
            fctxs, ctx2fctx = getfilestack(self.stack, path, seenfctxs)
            # ignore symbolic links or binary, or unchanged files
708 709 710 711 712
            if any(
                f.islink() or stringutil.binary(f.data())
                for f in [targetfctx] + fctxs
                if not isinstance(f, emptyfilecontext)
            ):
713 714 715 716 717
                continue
            if targetfctx.data() == fctxs[-1].data() and not editopt:
                continue
            seenfctxs.update(fctxs[1:])
            self.fctxmap[path] = ctx2fctx
718 719 720
            fstate = filefixupstate(fctxs, path, ui=self.ui, opts=self.opts)
            if fm is not None:
                fm.startitem()
721 722 723
                fm.plain(b'showing changes for ')
                fm.write(b'path', b'%s\n', path, label=b'absorb.path')
                fm.data(linetype=b'path')
724
            fstate.diffwith(targetfctx, fm)
725 726
            self.fixupmap[path] = fstate
            self.paths.append(path)
727
            self.ctxaffected.update(fstate.ctxaffected)
728 729 730

    def apply(self):
        """apply fixups to individual filefixupstates"""
731
        for path, state in pycompat.iteritems(self.fixupmap):
732
            if self.ui.debugflag:
733
                self.ui.write(_(b'applying fixups to %s\n') % path)
734 735 736 737 738
            state.apply()

    @property
    def chunkstats(self):
        """-> {path: chunkstats}. collect chunkstats from filefixupstates"""
739 740
        return {
            path: state.chunkstats
741
            for path, state in pycompat.iteritems(self.fixupmap)
742
        }
743 744 745

    def commit(self):
        """commit changes. update self.finalnode, self.replacemap"""
746
        with self.repo.transaction(b'absorb') as tr:
747 748
            self._commitstack()
            self._movebookmarks(tr)
749
            if self.repo[b'.'].node() in self.replacemap:
750 751
                self._moveworkingdirectoryparent()
            self._cleanupoldcommits()
752 753 754 755 756 757 758 759
        return self.finalnode

    def printchunkstats(self):
        """print things like '1 of 2 chunk(s) applied'"""
        ui = self.ui
        chunkstats = self.chunkstats
        if ui.verbose:
            # chunkstats for each file
760
            for path, stat in pycompat.iteritems(chunkstats):
761
                if stat[0]:
762
                    ui.write(
763
                        _(b'%s: %d of %d chunk(s) applied\n')
764 765
                        % (path, stat[0], stat[1])
                    )
766 767 768 769
        elif not ui.quiet:
            # a summary for all files
            stats = chunkstats.values()
            applied, total = (sum(s[i] for s in stats) for i in (0, 1))
770
            ui.write(_(b'%d of %d chunk(s) applied\n') % (applied, total))
771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786

    def _commitstack(self):
        """make new commits. update self.finalnode, self.replacemap.
        it is splitted from "commit" to avoid too much indentation.
        """
        # last node (20-char) committed by us
        lastcommitted = None
        # p1 which overrides the parent of the next commit, "None" means use
        # the original parent unchanged
        nextp1 = None
        for ctx in self.stack:
            memworkingcopy = self._getnewfilecontents(ctx)
            if not memworkingcopy and not lastcommitted:
                # nothing changed, nothing commited
                nextp1 = ctx
                continue
787 788 789 790
            willbecomenoop = ctx.files() and self._willbecomenoop(
                memworkingcopy, ctx, nextp1
            )
            if self.skip_empty_successor and willbecomenoop:
791 792
                # changeset is no longer necessary
                self.replacemap[ctx.node()] = None
793
                msg = _(b'became empty and was dropped')
794 795 796 797 798 799 800
            else:
                # changeset needs re-commit
                nodestr = self._commitsingle(memworkingcopy, ctx, p1=nextp1)
                lastcommitted = self.repo[nodestr]
                nextp1 = lastcommitted
                self.replacemap[ctx.node()] = lastcommitted.node()
                if memworkingcopy:
801
                    if willbecomenoop:
802
                        msg = _(b'%d file(s) changed, became empty as %s')
803 804 805
                    else:
                        msg = _(b'%d file(s) changed, became %s')
                    msg = msg % (
806 807 808
                        len(memworkingcopy),
                        self._ctx2str(lastcommitted),
                    )
809
                else:
810
                    msg = _(b'became %s') % self._ctx2str(lastcommitted)
811
            if self.ui.verbose and msg:
812
                self.ui.write(_(b'%s: %s\n') % (self._ctx2str(ctx), msg))
813 814 815 816
        self.finalnode = lastcommitted and lastcommitted.node()

    def _ctx2str(self, ctx):
        if self.ui.debugflag:
817
            return b'%d:%s' % (ctx.rev(), ctx.hex())
818
        else:
819
            return b'%d:%s' % (ctx.rev(), node.short(ctx.node()))
820 821 822 823 824 825 826 827 828

    def _getnewfilecontents(self, ctx):
        """(ctx) -> {path: str}

        fetch file contents from filefixupstates.
        return the working copy overrides - files different from ctx.
        """
        result = {}
        for path in self.paths:
829
            ctx2fctx = self.fctxmap[path]  # {ctx: fctx}
830 831 832 833 834 835 836 837 838 839 840
            if ctx not in ctx2fctx:
                continue
            fctx = ctx2fctx[ctx]
            content = fctx.data()
            newcontent = self.fixupmap[path].getfinalcontent(fctx)
            if content != newcontent:
                result[fctx.path()] = newcontent
        return result

    def _movebookmarks(self, tr):
        repo = self.repo
841 842
        needupdate = [
            (name, self.replacemap[hsh])
843
            for name, hsh in pycompat.iteritems(repo._bookmarks)
844 845
            if hsh in self.replacemap
        ]
846 847 848 849 850
        changes = []
        for name, hsh in needupdate:
            if hsh:
                changes.append((name, hsh))
                if self.ui.verbose:
851
                    self.ui.write(
852
                        _(b'moving bookmark %s to %s\n') % (name, node.hex(hsh))
853
                    )
854 855 856
            else:
                changes.append((name, None))
                if self.ui.verbose:
857
                    self.ui.write(_(b'deleting bookmark %s\n') % name)
858 859 860 861 862
        repo._bookmarks.applychanges(repo, tr, changes)

    def _moveworkingdirectoryparent(self):
        if not self.finalnode:
            # Find the latest not-{obsoleted,stripped} parent.
863
            revs = self.repo.revs(b'max(::. - %ln)', self.replacemap.keys())
864 865 866 867 868 869 870 871 872 873
            ctx = self.repo[revs.first()]
            self.finalnode = ctx.node()
        else:
            ctx = self.repo[self.finalnode]

        dirstate = self.repo.dirstate
        # dirstate.rebuild invalidates fsmonitorstate, causing "hg status" to
        # be slow. in absorb's case, no need to invalidate fsmonitorstate.
        noop = lambda: 0
        restore = noop
874
        if util.safehasattr(dirstate, '_fsmonitorstate'):
875
            bak = dirstate._fsmonitorstate.invalidate
876

877 878
            def restore():
                dirstate._fsmonitorstate.invalidate = bak
879

880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898
            dirstate._fsmonitorstate.invalidate = noop
        try:
            with dirstate.parentchange():
                dirstate.rebuild(ctx.node(), ctx.manifest(), self.paths)
        finally:
            restore()

    @staticmethod
    def _willbecomenoop(memworkingcopy, ctx, pctx=None):
        """({path: content}, ctx, ctx) -> bool. test if a commit will be noop

        if it will become an empty commit (does not change anything, after the
        memworkingcopy overrides), return True. otherwise return False.
        """
        if not pctx:
            parents = ctx.parents()
            if len(parents) != 1:
                return False
            pctx = parents[0]
899 900
        if ctx.branch() != pctx.branch():
            return False
901 902
        if ctx.extra().get(b'close'):
            return False
903
        # ctx changes more files (not a subset of memworkingcopy)
904
        if not set(ctx.files()).issubset(set(memworkingcopy)):
905
            return False
906
        for path, content in pycompat.iteritems(memworkingcopy):
907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924
            if path not in pctx or path not in ctx:
                return False
            fctx = ctx[path]
            pfctx = pctx[path]
            if pfctx.flags() != fctx.flags():
                return False
            if pfctx.data() != content:
                return False
        return True

    def _commitsingle(self, memworkingcopy, ctx, p1=None):
        """(ctx, {path: content}, node) -> node. make a single commit

        the commit is a clone from ctx, with a (optionally) different p1, and
        different file contents replaced by memworkingcopy.
        """
        parents = p1 and (p1, node.nullid)
        extra = ctx.extra()
925 926
        if self._useobsolete and self.ui.configbool(b'absorb', b'add-noise'):
            extra[b'absorb_source'] = ctx.hex()
927 928 929 930 931 932 933 934 935 936 937 938

        desc = rewriteutil.update_hash_refs(
            ctx.repo(),
            ctx.description(),
            {
                oldnode: [newnode]
                for oldnode, newnode in self.replacemap.items()
            },
        )
        mctx = overlaycontext(
            memworkingcopy, ctx, parents, extra=extra, desc=desc
        )
939
        return mctx.commit()
940 941 942 943 944 945

    @util.propertycache
    def _useobsolete(self):
        """() -> bool"""
        return obsolete.isenabled(self.repo, obsolete.createmarkersopt)

946
    def _cleanupoldcommits(self):
947 948
        replacements = {
            k: ([v] if v is not None else [])
949
            for k, v in pycompat.iteritems(self.replacemap)
950
        }
951
        if replacements:
952
            scmutil.cleanupnodes(
953
                self.repo, replacements, operation=b'absorb', fixphase=True
954 955
            )

956 957 958 959
    @util.propertycache
    def skip_empty_successor(self):
        return rewriteutil.skip_empty_successor(self.ui, b'absorb')

960 961 962 963 964 965 966 967 968 969 970 971 972 973

def _parsechunk(hunk):
    """(crecord.uihunk or patch.recordhunk) -> (path, (a1, a2, [bline]))"""
    if type(hunk) not in (crecord.uihunk, patch.recordhunk):
        return None, None
    path = hunk.header.filename()
    a1 = hunk.fromline + len(hunk.before) - 1
    # remove before and after context
    hunk.before = hunk.after = []
    buf = util.stringio()
    hunk.write(buf)
    patchlines = mdiff.splitnewlines(buf.getvalue())
    # hunk.prettystr() will update hunk.removed
    a2 = a1 + hunk.removed
974
    blines = [l[1:] for l in patchlines[1:] if not l.startswith(b'-')]
975 976
    return path, (a1, a2, blines)

977

978 979 980 981 982 983 984 985 986 987 988 989 990 991 992
def overlaydiffcontext(ctx, chunks):
    """(ctx, [crecord.uihunk]) -> memctx

    return a memctx with some [1] patches (chunks) applied to ctx.
    [1]: modifications are handled. renames, mode changes, etc. are ignored.
    """
    # sadly the applying-patch logic is hardly reusable, and messy:
    # 1. the core logic "_applydiff" is too heavy - it writes .rej files, it
    #    needs a file stream of a patch and will re-parse it, while we have
    #    structured hunk objects at hand.
    # 2. a lot of different implementations about "chunk" (patch.hunk,
    #    patch.recordhunk, crecord.uihunk)
    # as we only care about applying changes to modified files, no mode
    # change, no binary diff, and no renames, it's probably okay to
    # re-invent the logic using much simpler code here.
993 994
    memworkingcopy = {}  # {path: content}
    patchmap = defaultdict(lambda: [])  # {path: [(a1, a2, [bline])]}
995 996 997 998
    for path, info in map(_parsechunk, chunks):
        if not path or not info:
            continue
        patchmap[path].append(info)
999
    for path, patches in pycompat.iteritems(patchmap):
1000 1001 1002 1003 1004 1005
        if path not in ctx or not patches:
            continue
        patches.sort(reverse=True)
        lines = mdiff.splitnewlines(ctx[path].data())
        for a1, a2, blines in patches:
            lines[a1:a2] = blines
1006
        memworkingcopy[path] = b''.join(lines)
1007 1008
    return overlaycontext(memworkingcopy, ctx)

1009

1010 1011 1012 1013 1014 1015 1016 1017
def absorb(ui, repo, stack=None, targetctx=None, pats=None, opts=None):
    """pick fixup chunks from targetctx, apply them to stack.

    if targetctx is None, the working copy context will be used.
    if stack is None, the current draft stack will be used.
    return fixupstate.
    """
    if stack is None:
1018 1019
        limit = ui.configint(b'absorb', b'max-stack-size')
        headctx = repo[b'.']
1020
        if len(headctx.parents()) > 1:
1021
            raise error.Abort(_(b'cannot absorb into a merge'))
1022
        stack = getdraftstack(headctx, limit)
1023
        if limit and len(stack) >= limit:
1024
            ui.warn(
1025 1026 1027 1028
                _(
                    b'absorb: only the recent %d changesets will '
                    b'be analysed\n'
                )
1029 1030
                % limit
            )
1031
    if not stack:
1032
        raise error.Abort(_(b'no mutable changeset to change'))
1033
    if targetctx is None:  # default to working copy
1034 1035 1036 1037 1038 1039 1040
        targetctx = repo[None]
    if pats is None:
        pats = ()
    if opts is None:
        opts = {}
    state = fixupstate(stack, ui=ui, opts=opts)
    matcher = scmutil.match(targetctx, pats, opts)
1041
    if opts.get(b'interactive'):
1042 1043
        diff = patch.diff(repo, stack[-1].node(), targetctx.node(), matcher)
        origchunks = patch.parsepatch(diff)
1044
        chunks = cmdutil.recordfilter(ui, origchunks, matcher)[0]
1045
        targetctx = overlaydiffcontext(stack[-1], chunks)
1046
    fm = None
1047 1048
    if opts.get(b'print_changes') or not opts.get(b'apply_changes'):
        fm = ui.formatter(b'absorb', opts)
1049 1050
    state.diffwith(targetctx, matcher, fm)
    if fm is not None:
1051
        fm.startitem()
Augie Fackler's avatar